Xingxing Wei
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1NLP×1
Frequent co-authors
Research Timeline
2026
MESA: Improving MoE Safety Alignment via Decentralized Expertise
MESA is a targeted alignment framework that decentralizes safety responsibilities across multiple experts in Mixture-of-Experts (MoE) LLMs using Optimal Transport theory, thereby improving safety robustness without sacrificing utility.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.AIcs.CLRecentMay 30, 2026
MESA: Improving MoE Safety Alignment via Decentralized Expertise
Yitong Sun, Yao Huang, Teng Li, Ranjie Duan +4 more
MESA is a targeted alignment framework that decentralizes safety responsibilities across multiple experts in Mixture-of-Experts (MoE) LLMs using Optimal Transport theory, thereby improving safety robu…
View →